pith. sign in

archive

Every paper Pith has read. Search by title, abstract, or pith.

14903 papers in cs.LG · page 4

  1. cs.RO 2026-05-21 reviewed
    Robots detect underspecified features via demo variation and query for fixes

    Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations

    Helena Merker +2

  2. cs.LG 2026-05-21 reviewed
    Test-time training raises jailbreak success rates to 95%

    Test-Time Training Undermines Safety Guardrails

    Simone Antonelli +2

  3. cs.CL 2026-05-21 reviewed
    FIM pretraining yields linear verbatim memorization growth

    Memorization Dynamics of Fill-in-the-Middle Pretraining

    Tobias von Arx +1

  4. cs.LG 2026-05-21 reviewed
    Random Feature Selection Outperforms Many State-of-the-Art Methods

    Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection

    Muhammad Rajabinasab +3

  5. cs.LG 2026-05-21 reviewed
    Models balance rules and exceptions only under specific geometries

    A mathematical theory of balancing relational generalization and memorization

    Luke Cheng +1

  6. q-bio.QM 2026-05-21 reviewed
    Bayesian models match frequentist SHD classification with better uncertainty

    Uncertainty-aware classification and triage of structural heart disease using electrocardiography and echocardiography metrics

    Mitchel J. Colebank

  7. cs.LG 2026-05-21 reviewed
    Relay channel lets diffusion LMs cut latency by 32%

    Learned Relay Representations for Forward-Thinking Discrete Diffusion Models

    Benjamin Rozonoyer +6

  8. cs.LG 2026-05-21 reviewed
    One extra gate makes exact certification exponential

    Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization

    Artur Back de Luca +1

  9. cs.LG 2026-05-21 reviewed
    Survival forests match centralized accuracy in federated medical data

    FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data

    Maryam Moradpour +5

  10. stat.ML 2026-05-21 reviewed
    Diffusion denoising score matching keeps bounds stable as modes separate

    Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation

    Benedikt L\"utke Schwienhorst +2

  11. cs.LG 2026-05-21 reviewed
    Online calibration cuts foundation model errors 3-6x under shift

    MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination

    Joss Armstrong

  12. cs.LG 2026-05-21 reviewed
    Entropy regularization needs non-degenerate information forces to work

    Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning

    Kim Phuc Tran

  13. cs.CL 2026-05-21 reviewed
    LIFT gives diffusion models up to 3x reasoning gains on math tests

    Learnability-Informed Fine-Tuning of Diffusion Language Models

    Shubham Parashar +7

  14. cs.LG 2026-05-21 reviewed
    Two-stage pipeline keeps sensitive mobile data on device for recommendations

    Building a privacy-preserving Federated Recommender system for mobile devices

    Aasheesh Singh

  15. cs.CL 2026-05-21 reviewed
    Linear program yields tokenizers within 1% of optimal

    Tokenisation via Convex Relaxations

    Jan Tempus +4

  16. cs.LG 2026-05-21 reviewed
    Neural demand model yields stable retail elasticities

    Integrable Elasticity via Neural Demand Potentials

    Carlos Heredia +1

  17. cs.LG 2026-05-21 reviewed
    Vector rewards produce diverse LLM outputs that raise search scores

    Vector Policy Optimization: Training for Diversity Improves Test-Time Search

    Ryan Bahlous-Boldi +8

  18. cs.LG 2026-05-21 reviewed
    Persistent 3D model and RGB memory improve curiosity exploration

    Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration

    Lily Goli +5

  19. cs.LG 2026-05-21 reviewed
  20. stat.ML 2026-05-21 reviewed
    Kernel density gradients yield conservative drifting at rate N^{-1/(d+4)}

    Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models

    Krishnakumar Balasubramanian

  21. cs.AI 2026-05-21 reviewed
    Agents boost scores by rewriting their own code

    MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems

    Qianshu Cai +7

  22. cs.AI 2026-05-21 reviewed
    KV cache guard cuts reconstruction leaks in multi-agent LLMs

    LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems

    Sadia Asif +4

  23. cs.SE 2026-05-21 reviewed
    FAME detects log anomalies per message with 76x less labeling

    FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection

    Huanchi Wang +5

  24. cs.LG 2026-05-21 reviewed
    Transcoders trace VLM grounding and predict hallucinations at 0.68 AUC

    Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models

    Dimitrios Damianos +4

  25. cs.LG 2026-05-21 reviewed
    Diffusion model generates continuous survival times from censored data

    SDPM: Survival Diffusion Probabilistic Model for Continuous-Time Survival Analysis

    Stanislav R. Kirpichenko +2

  26. cs.LG 2026-05-21 reviewed
    Mamba model hits 76.8% accuracy on eye-gaze cognitive load

    MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data

    Amir Mousavi +7

  27. cs.LG 2026-05-21 reviewed
    ECG foundation models adapt to wearables for cognitive load

    CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessment via Lead Adaptation

    Amir Mousavi +7

  28. cs.LG 2026-05-21 reviewed
    Leave-one-out predictor fixes uniform diffusion mismatch

    Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

    Samson Gourevitch +6

  29. cs.LG 2026-05-21 reviewed
    Heavy hitter detector enables deeper private random forests

    Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees

    Christian Janos Lebeda +3

  30. cs.LG 2026-05-21 reviewed
    Smart grid detection uses 75% fewer measurements

    Cyber-Physical Anomaly Detection in IoT-Enabled Smart Grids Using Machine Learning and Metaheuristic Feature Optimization

    Adis Alihod\v{z}i\'c +2

  31. cs.RO 2026-05-21 reviewed
    Multi-agent RL drones beat humans with half the collisions

    Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning

    Ismail Geles +3

  32. cs.LG 2026-05-21 reviewed
    Plug-in losses approximate EDL objectives with decaying error

    Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier

    Berk Hayta +3

  33. cs.LG 2026-05-21 reviewed
    Bilevel LoRA optimization composes 101 concepts without forgetting

    SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation

    Javad Parsa +4

  34. cs.LG 2026-05-21 reviewed
    Ternary trees boost decided accuracy by flagging uncertain cases

    Ternary Decision Trees with Locally-Adaptive Uncertainty Zones

    William Smits

  35. cs.LG 2026-05-21 reviewed
    Proxy method sets new accuracy standard for Shapley interactions

    Proxy-Based Approximation of Shapley and Banzhaf Interactions

    Santo M. A. R. Thies +5

  36. cs.LG 2026-05-21 reviewed
    ProxySHAP lowers error in Shapley interaction estimates

    Proxy-Based Approximation of Shapley and Banzhaf Interactions

    Santo M. A. R. Thies +5

  37. cs.LG 2026-05-21 reviewed
    Cheap PoE defense narrows gap under adaptive distillation attacks

    The Distillation Game: Adaptive Attacks & Efficient Defenses

    Youssef Allouah +3

  38. math.OC 2026-05-21 reviewed
    Equivalence of manifold conditions simplifies intersection optimization

    Optimization over the intersection of manifolds

    Yan Yang +2

  39. cs.LG 2026-05-21 reviewed
    State distributions shape post-training outcomes more than loss functions

    Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation

    Dong Nie

  40. cs.LG 2026-05-21 reviewed
    Multi-task operator learning matches single-task rates

    Multiple Neural Operators Achieve Near-Optimal Rates for Multi-Task Learning

    Adrien Weihs +1

  41. cs.LG 2026-05-21 reviewed
    Full covariance matching cuts DDPM path error to O(1/T^2)

    The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler

    Md Sahil Akhtar +3

  42. cs.LG 2026-05-21 reviewed
    One feature marks GPT-2 failures on keys prompts

    Reading Task Failure Off the Activations: A Sparse-Feature Audit of GPT-2 Small on Indirect Object Identification

    Mahdi Nasermoghadasi

  43. cs.SD 2026-05-21 reviewed
    Diffusion models match discrete models for live music

    Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators

    Zachary Novack +10

  44. cs.AI 2026-05-21 reviewed
    Conversation history pulls LLM judgments toward its tone

    AMEL: Accumulated Message Effects on LLM Judgments

    Sid-ali Temkit

  45. cs.LG 2026-05-21 reviewed
    Relativised options let agents reuse experience across goals in offline RL

    Abstraction for Offline Goal-Conditioned Reinforcement Learning

    Clarisse Wibault +4

  46. cs.LG 2026-05-21 reviewed
    Stochastic rescue recovers signals lost to RLVR clipping

    Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals

    Shuo Yang +10

  47. cs.LG 2026-05-21 reviewed
    β-VAE posterior collapse prunes latent modes by utility

    Posterior Collapse as Automatic Spectral Pruning

    Johannes Hirn

  48. cs.LG 2026-05-21 reviewed
    New VAE model classifies time series without quadratic attention

    ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification

    Jos\'e Alberto Rodr\'iguez +4

  49. cs.CV 2026-05-21 reviewed
    Disentangling vision-language embeddings without added dimensions

    Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models

    Piotr Kubaty +5

  50. math.CO 2026-05-21 reviewed
    Three bounded-complexity notions for fuzzy functions are equivalent

    Holographic functions and neural networks

    Balazs Szegedy